Ultrasound Image-Based Deep Features and Radiomics for the Discrimination of Small Fat-Poor Angiomyolipoma and Small Renal Cell Carcinoma

We evaluated the performance of ultrasound image-based deep features and radiomics for differentiating small fat-poor angiomyolipoma (sfp-AML) from small renal cell carcinoma (SRCC). This retrospective study included 194 patients with pathologically proven small renal masses (diameter ≤4 cm; 67 in t...

Full description

Saved in:
Bibliographic Details
Published in:Ultrasound in medicine & biology Vol. 49; no. 2; p. 560
Main Authors: Zhang, Li, Sun, Kui, Shi, Liting, Qiu, Jianfeng, Wang, Ximing, Wang, Shumin
Format: Journal Article
Language:English
Published: England 01.02.2023
Subjects:
Angiomyolipoma - diagnostic imaging
Angiomyolipoma - pathology
Carcinoma, Renal Cell - diagnostic imaging
Carcinoma, Renal Cell - pathology
Humans
Kidney Neoplasms - diagnostic imaging
Kidney Neoplasms - pathology
Retrospective Studies
Ultrasonography
Small renal cell carcinoma
Ultrasound images
Small fat-poor angiomyolipoma
Deep features
Radiomics
ISSN:1879-291X, 1879-291X
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We evaluated the performance of ultrasound image-based deep features and radiomics for differentiating small fat-poor angiomyolipoma (sfp-AML) from small renal cell carcinoma (SRCC). This retrospective study included 194 patients with pathologically proven small renal masses (diameter ≤4 cm; 67 in the sfp-AML group and 127 in the SRCC group). We obtained 206 and 364 images from the sfp-AML and SRCC groups with experienced radiologist identification, respectively. We extracted 4024 deep features from the autoencoder neural network and 1497 radiomics features from the Pyradiomics toolbox; the latter included first-order, shape, high-order, Laplacian of Gaussian and Wavelet features. All subjects were allocated to the training and testing sets with a ratio of 3:1 using stratified sampling. The least absolute shrinkage and selection operator (LASSO) regression model was applied to select the most diagnostic features. Support vector machine (SVM) was adopted as the discriminative classifier. An optimal feature subset including 45 deep and 7 radiomics features was screened by the LASSO model. The SVM classifier achieved good performance in discriminating between sfp-AMLs and SRCCs, with areas under the curve (AUCs) of 0.96 and 0.85 in the training and testing sets, respectively. The classifier built using deep and radiomics features can accurately differentiate sfp-AMLs from SRCCs on ultrasound imaging.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1879-291X
1879-291X
DOI:10.1016/j.ultrasmedbio.2022.10.009